Invertible Residual Networks

i-ResNet：通过变分解量化和结构设计改进流模型.

Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design

Flow++：通过变分解量化和结构设计改进流模型.

Improving Variational Inference with Inverse Autoregressive Flow

IAF：使用逆自回归流改进变分推断.

Contrastive Learning for Unpaired Image-to-Image Translation

无配对数据图像到图像翻译中的对比学习.

TFPose: Direct Human Pose Estimation with Transformers

TFPose: 基于Transformer的2D人体关节点回归.

Masked Autoregressive Flow for Density Estimation

MAF：使用掩码自回归流进行密度估计.